The Text-Score Allocation Model : Finding Latent Topics of Online Review Documents and Multi-Item Ratings

Katsumata, Sotaro; Kim, Seungjin

このアイテムのアクセス数:5件（2020-10-23 15:58 集計）

このアイテムへのリンクには次のURLをご利用ください:http://hdl.handle.net/11094/73808

論文情報

タイトル	The Text-Score Allocation Model : Finding Latent Topics of Online Review Documents and Multi-Item Ratings
著者	Katsumata, Sotaro Katsumata, Sotaro
著者	Kim, Seungjin Kim, Seungjin
キーワード等	Topic Modeling
	Customer Reviews
	Forecasting
抄録	This study focuses on online review data in which comments are written in natural languages and evaluations are attached as integers. This study develops a topic model incorporating both natural languages and evaluation scores, expanding latent Dirichlet allocation (LDA). The model consists of two components: LDA and a Dirichlet-binomial clustering model. The latter assumes binomial distributions for the review scores. Since the model assumes conjugate distributions, we can apply a fast and stable estimator based on collapsed Gibbs sampling to estimate the parameters. Further,the model enables us to examine the relationship between vocabulary words and review scores based on the topic allocation results.
公開者	Graduate School of Economics and Osaka School of International Public Policy (OSIPP) Osaka University
掲載誌名	Discussion Papers In Economics And Business
巻	20-01
開始ページ	1
終了ページ	35
刊行年月	2020-01
URL	http://hdl.handle.net/11094/73808
関連情報	http://www2.econ.osaka-u.ac.jp/econ_society/dp/2001.pdf
言語	英語
カテゴリ	ディスカッション／ワーキング・ペーパー DP/WP

著者版フラグ	none
NII資源タイプ	テクニカルレポート
ローカル資源タイプ	ディスカッション／ワーキング・ペーパー
dcmi資源タイプ	text
DCTERMS.bibliographicCitation	Discussion Papers In Economics And Business.20-01 P.1-P.35
DC.title	The Text-Score Allocation Model : Finding Latent Topics of Online Review Documents and Multi-Item Ratings
DC.creator	Katsumata, Sotaro
DC.creator	Kim, Seungjin
DC.publisher	Graduate School of Economics and Osaka School of International Public Policy (OSIPP) Osaka University
DC.language" scheme="DCTERMS.RFC1766	英語
DCTERMS.issued" scheme="DCTERMS.W3CDTF	2020-01
DC.identifier" scheme="DCTERMS.URI	http://hdl.handle.net/11094/73808
DC.relation	http://www2.econ.osaka-u.ac.jp/econ_society/dp/2001.pdf
DC.subject	Topic Modeling
	Customer Reviews
	Forecasting
DCTERMS.abstract	This study focuses on online review data in which comments are written in natural languages and evaluations are attached as integers. This study develops a topic model incorporating both natural languages and evaluation scores, expanding latent Dirichlet allocation (LDA). The model consists of two components: LDA and a Dirichlet-binomial clustering model. The latter assumes binomial distributions for the review scores. Since the model assumes conjugate distributions, we can apply a fast and stable estimator based on collapsed Gibbs sampling to estimate the parameters. Further,the model enables us to examine the relationship between vocabulary words and review scores based on the topic allocation results.
citation_title	The Text-Score Allocation Model : Finding Latent Topics of Online Review Documents and Multi-Item Ratings
citation_author	Katsumata, Sotaro
citation_author	Kim, Seungjin
citation_publisher	Graduate School of Economics and Osaka School of International Public Policy (OSIPP) Osaka University
citation_language	英語
citation_date	2020-01
citation_journal_title	Discussion Papers In Economics And Business
citation_volume	20-01
citation_firstpage	1
citation_lastpage	35
citation_public_url	http://hdl.handle.net/11094/73808
citation_keywords	Topic Modeling
	Customer Reviews
	Forecasting

論文情報

論文詳細を表示